Jörn,

I would volunteer to write the documentation piece and samples when I
understand how that works. I have seen this script from a book and now I am
in the process of understanding it.

#!/bin/sh
#
# Usage: ./opennlp-coreference.sh < input.txt > coref.txt

OPENNLP_HOME=~gwilcock/Tools/opennlp-tools-1.3.0
export OPENNLP_HOME

WORDNET_HOME=~gwilcock/Tools/wordnet-2.0
export WORDNET_HOME

CLASSPATH=.:\
$OPENNLP_HOME/output/opennlp-tools-1.3.0.jar:\
$OPENNLP_HOME/lib/maxent-2.4.0.jar:\
$OPENNLP_HOME/lib/trove.jar:\
$OPENNLP_HOME/lib/jwnl-1.3.3.jar
export CLASSPATH

java opennlp.tools.lang.english.SentenceDetector \
  $OPENNLP_HOME/models/english/sentdetect/EnglishSD.bin.gz |
java opennlp.tools.lang.english.Tokenizer \
  $OPENNLP_HOME/models/english/tokenize/EnglishTok.bin.gz |
java -Xmx1024m opennlp.tools.lang.english.TreebankParser -d \
  $OPENNLP_HOME/models/english/parser |
java -Xmx1024m opennlp.tools.lang.english.NameFinder -parse \
  $OPENNLP_HOME/models/english/namefind/*.bin.gz |
java -Xmx1024m -DWNSEARCHDIR=$WORDNET_HOME/dict -Duser.language=en \
  opennlp.tools.lang.english.TreebankLinker \
  $OPENNLP_HOME/models/english/coref


On Wed, Jun 13, 2012 at 10:46 AM, Jörn Kottmann <[email protected]> wrote:

> Hello,
>
> the main method is actually a good example on how to use
> it. So have a look at it.
>
> Let me know if there are further questions. We still need to update that
> part of the documentation. There should be a proper sample and explanation.
>
> Hope that helps,
> Jörn
>
>
> On 06/13/2012 06:42 PM, Carlos Scheidecker wrote:
>
>> The opennlp.tools.lang.english.**TreebankLinker has a Main method to
>> perform
>> Coreference resolutions.
>>
>> One can call that from the command line.
>>
>> I would like to know how to use that with the Java API. Can anyone provide
>> an example?
>>
>> Thanks,
>>
>> Carlos.
>>
>> I've also found this explanation here:
>> http://mail-archives.apache.**org/mod_mbox/opennlp-users/**
>> 201112.mbox/%3C4ED76AF3.**[email protected]%3E<http://mail-archives.apache.org/mod_mbox/opennlp-users/201112.mbox/%[email protected]%3E>
>>
>> I now got it running with 1.5.
>> You need to do the following.
>>
>> Use our Parser to parse an input article.
>>
>> Use the TreebankNameFinder to add names to your parsed article (its now
>> in the trunk, see OPENNLP-407).
>> I used this command:
>> java -cp ... TreebankNameFinder -parse ner/date.bin ner/location.bin
>> ner/money.bin ner/organization.bin ner/percentage.bin ner/person.bin
>> ner/time.bin
>>
>> The names of models does matter. When you get the models from the
>> website rename them as I did.
>>
>> Now you need to run the TreebankLinker. It just needs the model
>> directory and you need to set WNSEARCHDIR
>> to your wordnet directory, e.g like this -DWNSEARCHDIR=wordnet/dict
>>
>> Now the TreebankLinker is ready to link mentions together.
>>
>> Let us know if you have issues to get this running.
>>
>> Hope this helps,
>> Jörn
>>
>>
>

Reply via email to